Learn More
Scaling up deep learning algorithms has been shown to lead to increased performance in benchmark tasks and to enable discovery of complex high-level features. Recent efforts to train extremely large networks (with over 1 billion parameters) have relied on cloud-like computing infrastructure and thousands of CPU cores. In this paper, we present technical(More)
Full end-to-end text recognition in natural images is a challenging problem that has received much attention recently. Traditional systems in this area have relied on elaborate models incorporating carefully hand-engineered features or large amounts of prior knowledge. In this paper, we take a different route and combine the representational power of large,(More)
—Reading text from photographs is a challenging problem that has received a significant amount of attention. Two key components of most systems are (i) text detection from images and (ii) character recognition, and many recent methods have been proposed to design better feature representations and models for both. In this paper, we apply methods recently(More)
In an order-preserving encryption scheme, the encryption algorithm produces ciphertexts that preserve the order of their plaintexts. Order-preserving encryption schemes have been studied intensely in the last decade, and yet not much is known about the security of these schemes. Very recently, Boneh et al. (Eurocrypt 2015) introduced a generalization of(More)
In a private database query system, a client issues queries to a database and obtains the results without learning anything else about the database and without the server learning the query. While previous work has yielded systems that can efficiently support disjunction queries, performing conjunction queries privately remains an open problem. In this(More)
Decision trees and random forests are common classifiers with widespread use. In this paper, we develop two protocols for privately evaluating decision trees and random forests. We operate in the standard two-party setting where the server holds a model (either a tree or a forest), and the client holds an input (a feature vector). At the conclusion of the(More)
In recent work Cheon, Han, Lee, Ryu, and Stehlé presented an attack on the multilinear map of Coron, Lepoint, and Tibouchi (CLT). They show that given many low-level encodings of zero, the CLT multilinear map can be completely broken, recovering the secret factorization of the CLT modulus. The attack is a generalization of the " zeroizing " attack of Garg,(More)
Machine learning is a key component of state-of-the-art systems in many application domains. Applied to many kinds of raw data, however, most learning algorithms are unable to make good predictions. In order to succeed, most learning algorithms are applied instead to " features " that represent higher-level concepts extracted from the raw data. These(More)
Autism spectrum disorders have been associated with maternally derived duplications that involve the imprinted region on the proximal long arm of chromosome 15. Here we describe a boy with a chromosome 15 duplication arising from a 3:1 segregation error of a paternally derived translocation between chromosome 15q13.2 and chromosome 9q34.12, which led to(More)